← Plugin catalog
Education & Research

Manusights

Manusights v1.3.0

Check citations & manuscripts

Create a free account to save this plugin.

From the developer

Declared capabilities

  • Check citations from any source
  • Look up journal AI policies
  • Start a manuscript preview

Cost & access

The plugin sells nothing: no tool description, tool result or skill names a price, links to a checkout or pricing page, or promotes an upgrade. If a user asks for a Full Review their account does not have, the skill says it is not on their account and links an informational page, https://manusights.com/chatgpt#full-review, which describes what the account adds and has no prices or checkout. Reference checks and journal policy lookups use public registries and Manusights' own records. Starting a preview needs a Manusights account but no payment. Reviews already on the user's Manusights account, including Full Reviews bought on manusights.com, can be read and downloaded.

Declared limitations

  • Writing a manuscript is out of scope
  • Finding new sources is out of scope
  • Journal metrics are out of scope

Onboarding example

Check the references in my attached draft for retractions, corrections and DOI mismatches.

View onboarding source →

Sources & dates

Developer declarations; not independently tested. Listing last checked Nov 5, 2026. Package observed Nov 4, 2026.

View package source →

Description

From the marketplace listing

Check the references in your draft or citations an AI assistant suggested. Preview your manuscript before submission. Check references: Paste a reference list, attach a draft, or ask to check citations from earlier in your conversation. Manusights looks each reference up in scholarly indexes and retraction databases, including Crossref and Retraction Watch. It shows which references are retracted or corrected, point to a different paper, or were not found in the sources checked. It notes details that differ from the record and can suggest a possible matching work for you to confirm. Results show the sources checked and the check time. For citation checks, only the references are sent to Manusights, never the manuscript. Look up journal AI rules: Ask about AI authorship, disclosure statements, AI-generated images, or reviewers' and editors' use of AI. Get Manusights' dated record with a link to the official policy. When the record needs rechecking or the page could not be fully read, the result says so and links the source. Preview a manuscript: Attach a PDF, Word, ODT, RTF, TXT, Markdown or LaTeX manuscript, up to 50 MB, for a readiness score, verdict, strengths and main risks reviewers may raise. This sends the attached manuscript to Manusights. You can also read reviews already on your Manusights account. To set up Manusights in ChatGPT, follow the sign-in and permission prompts to connect your Manusights account. Review the requested access before allowing the connection. Sign in with Google, an emailed code or a password. Manuscript previews and saved reviews use the connected account. What the checks cover: Results show what the sources hold. Matching a record does not show that a reference supports a claim, and "not found" can also mean a typo, a very recent paper or a source the indexes do not cover. Long lists are split across several checks. Policy coverage varies by journal. Manusights does not write or rewrite manuscripts.

Language: English · Automatically detected from descriptions.

Matches for “HS code”

Exact text from the indicated source. A mention alone does not establish support for your task.

Publisher full description

Check the references in your draft or citations an AI assistant suggested. Preview your manuscript before submission. Check references: Paste a reference list, attach a draft, or ask to check citations from earlier in your conversation. Manusights looks each reference up in scholarly indexes and retraction databases, including Crossref and Retraction Watch. It shows which references are retracted or corrected, point to a different paper, or were not found in the sources checked. It notes details that differ from the record and can suggest a possible matching work for you to confirm. Results show the sources checked and the check time. For citation checks, only the references are sent to Manusights, never the manuscript. Look up journal AI rules: Ask about AI authorship, disclosure statements, AI-generated images, or reviewers' and editors' use of AI. Get Manusights' dated record with a link to the official policy. When the record needs rechecking or the page could not be fully read, the result says so and links the source. Preview a manuscript: Attach a PDF, Word, ODT, RTF, TXT, Markdown or LaTeX manuscript, up to 50 MB, for a readiness score, verdict, strengths and main risks reviewers may raise. This sends the attached manuscript to Manusights. You can also read reviews already on your Manusights account. To set up Manusights in ChatGPT, follow the sign-in and permission prompts to connect your Manusights account. Review the requested access before allowing the connection. Sign in with Google, an emailed code or a password. Manuscript previews and saved reviews use the connected account. What the checks cover: Results show what the sources hold. Matching a record does not show that a reference supports a claim, and "not found" can also mean a typo, a very recent paper or a source the indexes do not cover. Long lists are split across several checks. Policy coverage varies by journal. Manusights does not write or rewrite manuscripts.

What changed

Earlier changes · 1 more observation days on this page

Keywords

Files & skills

File archives

Plugin package8 files · 18.3 KBBrowse files →
Skill instructions
check-before-submission4.64 KB

View saved version →

---
name: check-before-submission
description: Check citations and manuscripts with Manusights. Use it whenever the user wants to know whether references exist, point to the right paper, or have been retracted or corrected, including citations an AI assistant gave earlier in the conversation, a draft's reference list or a literature review; when they want a journal's AI-use and disclosure rules; or when they want a readiness preview of an attached manuscript before submission.
---

Explicit instructions from the user take priority over these steps. Manusights' results say how to report them; follow that guidance.

## Check references

1. Collect every reference the user wants checked: from their message, an
   attached draft, or earlier in this conversation. Send citations you gave
   earlier exactly as you gave them; do not correct, replace or defend them
   first.
2. Call `check_references` with every reference, with or without a DOI. For
   a whole list, such as the References section of an attached paper or a
   bibliography, send it exactly as written in `reference_list`, and keep
   calling with `start_at` as the result says until the whole list is
   checked. For a few references, send one item each, the reference exactly
   as written in `text`, plus any other field you can read reliably. Never
   check only a sample of a list.
   When the original list's count is known, pass it as
   `expected_reference_count` if that field is declared by the tool, and
   compare it with the returned `progress.total`. It is the count of the
   whole original list, not the current part. If the counts differ, resend
   the complete original list; do not lower the expected count, silently
   omit entries, or treat `next_start_at: null` for a shortened list as
   completion. If the tool asks for numbered lines, preserve existing
   reference numbers, or add sequential list labels without changing the
   citation text. Clarify uncertain boundaries instead of inventing entries.
   If the complete input cannot be sent, state exactly what
   remains unchecked and why.
3. Report the result the way its `how_to_report` says. Give each row's status
   and `detail` as returned; do not restate a status in stronger or softer
   words.
4. Never call a reference fake, fabricated or verified, and never call a list
   clean. If a reference you suggested is flagged or unchecked, say so
   plainly. Show a suggested record only as a possible match for the user to
   confirm; never replace a reference with it. Manusights does not judge
   whether a source supports a claim; label any view of your own, on that or
   anything else, as yours, apart from Manusights' results.

## Journal AI policy

1. Call `get_journal_ai_policy` with the journal's name or ISSN exactly as
   the user supplied it, including a possible typo. Do not silently correct
   the spelling, expand an ambiguous name, or replace it with another
   journal before the first lookup. If the intended journal is unclear,
   ask the user to confirm it. When an unmatched result offers
   `name_suggestions`, present them as possible names for the user to
   confirm; do not look up a suggested name until the user confirms it or
   treat it as a confirmed policy match.
2. State only the rules the result returns, with the date they were checked
   and the official policy link. When the result says it cannot state the
   rules, give its reason and the link instead.

## Manuscript preview

1. Call `review_manuscript` with the attached file. Pass `target_journal`
   only when the user named one.
2. A preview takes a few minutes. Read it with `get_manuscript_review` using
   the same `review_id`, waiting as the result says between calls; do not
   start another preview to check progress. While it is processing, report
   its status only; do not add your own critique or predict the findings. If
   the conversation stops first, tell the user they can ask you to retrieve
   the result.
3. When it is ready, report the findings as returned.
4. Mention a Full Review only when the result shows one already on the
   user's account, and then only its status or download link as returned. If
   the user asks for a Full Review the account does not have, say it is not on
   their account and link https://manusights.com/chatgpt#full-review, which
   describes it. Do not name a price or encourage a purchase.

## Earlier reviews

Use `list_manuscript_reviews` to show the reviews on the user's account, and
`get_manuscript_review` to open one.

Report results as returned. Do not add issues, scores, citations or journal
facts the tools did not return, invent fixes, or rewrite the manuscript. Keep
the author's own interpretation distinct from Manusights' findings.

Referenced files: 2 — file references are metadata, not package contents.

Release notes

Flag a DOI that opens a different paper, and name the cited paper when it is on record under another DOI. Read more reference-list formats exactly: lists with section headings, bullets, tables, DOIs on their own line and lists written on one line. Continue long checks of separate references in parts.

Declared in the saved package. Remote tools may change independently.

Package details

Publisher declarations from the archived package. These are separate from our research and the live service's terms.

Package author
Manusights
Keywords
See keywords
Getting started skill
./skills/check-before-submission/SKILL.md
Commerce declaration
Does not support commerceThis does not establish whether access is free or paid.
Review scenarios
5 positive · 3 negativeScenario counts, not test results.

Declared capabilities

  • Check citations from any source
  • Look up journal AI policies
  • Start a manuscript preview
  • Read manuscript reviews

Package observed Nov 4, 2026.

Technical details
First seen
Oct 24, 2026 · 12:40 UTC
Last seen
Nov 5, 2026 · 00:00 UTC
Collection status
Collected

plugin_asdk_app_6abe9a3cdf3c819191d8d505466917f1

Download plugin data (JSON)